Learning Connected Attentions for Convolutional Neural Networks-猫眼课题宝

DOI：

10.1109/icme51207.2021.9428397

发表时间：

2021-07

期刊：

2021 IEEE International Conference on Multimedia and Expo (ICME)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Xu Ma;Jingda Guo;Sihai Tang;Zhinan Qiao;Qi Chen;Qing Yang;Song Fu

虽然自注意机制在许多视觉任务中表现出了良好的效果，但它一次只考虑当前特征。我们表明，这种方式不能充分利用注意力机制。在本文中，我们提出了深度连接注意力网络（DCANet），这是一种新颖的设计，可以在不修改内部结构的情况下提高CNN模型中的注意力模块。为了实现这一点，我们互连相邻的注意力块，使注意力块之间的信息流成为可能。使用DCANet，CNN模型中的所有注意力块都被联合训练，这提高了注意力学习的能力。我们的DCANet是通用的。它不限于特定的注意力模块或基础网络架构。在ImageNet和MS COCO基准测试上的实验结果表明，DCANet在所有测试用例中都以最小的额外计算开销始终优于最先进的注意力模块。该代码可从以下网址获得：https://github.com/13952522076/DCANet。

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present Deep Connected Attention Network (DCANet), a novel design that boosts attention modules in a CNN model without any modification of the internal structure. To achieve this, we interconnect adjacent attention blocks, making information flow among attention blocks possible. With DCANet, all attention blocks in a CNN model are trained jointly, which improves the ability of attention learning. Our DCANet is generic. It is not limited to a specific attention module or base network architecture. Experimental results on ImageNet and MS COCO benchmarks show that DCANet consistently outperforms the state-of-the-art attention modules with a minimal additional computational overhead in all test cases. The code is available at: https://github.com/13952522076/DCANet.

Learning Connected Attentions for Convolutional Neural Networks

文献摘要

相似文献